Health Gorilla

# Fix list: Health Gorilla

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/health-gorilla, the October 2026 research run, assessed 14 October 2026. Grade C, 59.3 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Health Gorilla: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Payments & pricing, 5 out of 100, up to 11.9 more on the total

Why it scored 5: Read with the hosted rubric. No x402, MPP or L402 (0). Fees are set case by case by business development (0). A sandbox exists but starts with a contact form, with no price stated (5 of 20). A person requests access and Health Gorilla provisions credentials (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 2. Reliability, 58 out of 100, up to 8.4 more on the total

Why it scored 58: Read with the hosted lines. status.healthgorilla.com on Statuspage with 11 components and history (20). In the last 90 days the API Server stopped answering for 16 minutes on 29 September 2026 after an internal backlog, and the P360 Responding Gateway lost CommonWell traffic for about 90 minutes on 5 August 2026 during a hosting provider's outage, marked critical. We read the second as a network-side outage and scored between minor and one major (15 of 30). Rate limits are enforced with no numbers (0). Backoff advice, `Retry-After` on async polling and `HG-Idempotency-Key` for POST retries (13 of 15). No SLA was found in public. The Enterprise SaaS Agreement was not read (0). The FHIR API and Patient360 are generally available (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Security & auth, 66 out of 100, up to 6 more on the total

Why it scored 66: OAuth 2.0 with scopes assigned per client at registration, tenant context and short-lived tokens. The JWT bearer assertion is signed HS256 with the shared client secret, and an implicit grant can be enabled (25 of 30). Scopes per resource and action, tenant isolation and user roles intersect on every token, but write scopes carry no documented confirmation step (14 of 20). Retrieved C-CDA and FHIR documents come from outside organisations with no prompt-injection guidance (3 of 15). Exchange activity is logged with request IDs, and Network Admin reports list transactions per patient (12 of 15). HITRUST r2, SOC 2 Type II and QHIN designation, a security contact in an expired security.txt page that is not at /.well-known, and no bug bounty (12 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Agent ergonomics, 72 out of 100, up to 4.6 more on the total

Why it scored 72: `_count` and `_offset` size searches and $everything, and C-CDA export condenses a record (15 of 25). Bundle `next` links, search and date filters (18 of 20). OperationOutcome bodies, request IDs and a troubleshooting page (17 of 20). `HG-Idempotency-Key` on POST with replay and 409 on conflict (17 of 20). No official SDK, and every call needs scopes and products provisioned for the tenant (5 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Transparency & trust, 61 out of 100, up to 3.4 more on the total

Made of editorial 38, provenance 83.

Why it scored 61: Closed service under API terms updated 22 January 2026, which allow termination at any time and amendment without notice (15 of 30). The privacy policy (30 August 2024) covers the website and platforms with no retention periods, and a separate notice covers patient access, with no public DPA (12 of 30). Release notes give dated changes, with no written deprecation policy (8 of 20). No sub-processor list or data location was found (3 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Terms of service: read, states 5 of the 7 things a reader expects, and has 2 clauses that cost points (4.3 of 10)
- Privacy policy: read, states 6 of the 8 things a reader expects (8.5 of 10)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 80 out of 100, up to 3.3 more on the total

Why it scored 80: Each reference page carries an OpenAPI 3.1 fragment, with no single specification file found (18 of 25). llms.txt and Markdown copies of every page (10). Pages name the required scope and explain workflows such as Patient360 retrieval and async polling (14 of 20). Inputs follow FHIR search parameters with value sets and profiles documented (10 of 15). curl examples, a status code table, OperationOutcome format and common error scenarios (13 of 15). Dated release notes with sandbox and production go-live dates, and FHIR R4 and STU3 versioned paths (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 7. Maintenance & community, 63 out of 100, up to 3.2 more on the total

Why it scored 63: Release 2637_6 went to production on 14 October 2026 (30). Releases 2637_5 (7 October), 2637_4, 2637_3 and others since August (20). Closed service with dated release notes and a support desk. We did not test support (10 of 15). No official SDK was found (0 of 15). Docs carry agent tool metadata and are updated through October 2026 (3 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: the Enterprise SaaS Agreement (July 2024) linked from the website terms page, including any SLA
- No rate limit numbers were found in the developer portal
- No official SDK or GitHub repository was confirmed, because the GitHub API rate-limited us

## Weaknesses

- No public prices. Fees are set case by case and the sandbox is requested by form
- Rate limits are enforced with no published numbers
- JWT bearer assertions are signed HS256 with the shared client secret
- The API terms allow termination or disabling of access at any time, with or without notice

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Send a fresh UUID in `HG-Idempotency-Key` on every POST and reuse it only when retrying the same payload
- Poll async operations no sooner than the `Retry-After` value and treat 454 as an expired result
- Follow `link.relation=next` in Bundles rather than building offsets yourself
- Expect mocked Patient360 data in sandbox unless network connectivity is enabled for the tenant
- Log `X-HG-Request-Id` from each response for support cases

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.